89575e469132238818a653ca714eb6a1

This model is a fine-tuned version of google-bert/bert-large-uncased-whole-word-masking on the nyu-mll/glue [cola] dataset. It achieves the following results on the evaluation set:

• Loss: 0.5635
• Data Size: 1.0
• Epoch Runtime: 27.9772
• Accuracy: 0.7803
• F1 Macro: 0.7238
• Rouge1: 0.7803
• Rouge2: 0.0
• Rougel: 0.7803
• Rougelsum: 0.7803

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.9917	0	1.3596	0.3115	0.2375	0.3105	0.0	0.3115	0.3115
No log	1	267	0.6856	0.0078	2.4317	0.5078	0.4710	0.5078	0.0	0.5059	0.5068
No log	2	534	0.6597	0.0156	2.2535	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6131	0.0312	3.0930	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6971	0.0625	4.2254	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.0374	5	1335	0.6117	0.125	6.3678	0.7275	0.5427	0.7275	0.0	0.7275	0.7275
0.5316	6	1602	0.5197	0.25	9.9263	0.7656	0.6468	0.7656	0.0	0.7656	0.7656
0.4435	7	1869	0.5456	0.5	15.3476	0.7773	0.6700	0.7773	0.0	0.7773	0.7773
0.3708	8.0	2136	0.5580	1.0	27.9062	0.8105	0.7531	0.8105	0.0	0.8105	0.8105
0.3485	9.0	2403	0.6413	1.0	27.0795	0.7832	0.6916	0.7832	0.0	0.7832	0.7832
0.3097	10.0	2670	0.5635	1.0	27.9772	0.7803	0.7238	0.7803	0.0	0.7803	0.7803

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1